EndoMUST：通过端到端多步自监督训练实现机器人内窥镜的单目深度估计
EndoMUST: Monocular Depth Estimation for Robotic Endoscopy via End-to-end Multi-step Self-supervised Training
AI总结：
针对机器人内窥镜自监督深度估计中的光照与干扰问题，提出多步高效微调框架EndoMUST，在SCARED和Hamlyn数据集上达到最先进性能，误差降低4%-10%。
摘要：
单目深度估计和自运动估计是稳定、准确且高效的机器人辅助内窥镜中场景感知和导航的重要任务。为了解决内窥镜场景中的光照变化和稀疏纹理问题，现有方法引入了包括光流、表观流和固有图像分解在内的多种技术。然而，对于内窥镜中自监督深度估计，多模块的有效训练策略对于处理光照问题和信息干扰仍然至关重要。因此，本文提出了一种具有多步高效微调的新框架。在端到端训练的每个周期中，该过程分为三个步骤，包括光流配准、多尺度图像分解和多重变换对齐。在每个步骤中，仅训练相关网络，不受无关信息的干扰。基于基础模型上的参数高效微调，所提出的方法在SCARED数据集上的自监督深度估计和Hamlyn数据集上的零样本深度估计中达到了最先进的性能，误差降低了4%至10%。本工作的评估代码已发布在https://github.com/BaymaxShao/EndoMUST。
英文摘要：
Monocular depth estimation and ego-motion estimation are significant tasks for scene perception and navigation in stable, accurate and efficient robot-assisted endoscopy. To tackle lighting variations and sparse textures in endoscopic scenes, multiple techniques including optical flow, appearance flow and intrinsic image decomposition have been introduced into the existing methods. However, the effective training strategy for multiple modules are still critical to deal with both illumination issues and information interference for self-supervised depth estimation in endoscopy. Therefore, a novel framework with multistep efficient finetuning is proposed in this work. In each epoch of end-to-end training, the process is divided into three steps, including optical flow registration, multiscale image decomposition and multiple transformation alignments. At each step, only the related networks are trained without interference of irrelevant information. Based on parameter-efficient finetuning on the foundation model, the proposed method achieves state-of-the-art performance on self-supervised depth estimation on SCARED dataset and zero-shot depth estimation on Hamlyn dataset, with 4\%$\sim$10\% lower error. The evaluation code of this work has been published on https://github.com/BaymaxShao/EndoMUST.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
